%0 Conference Paper %F Oral %T Real Time Semi-dense Point Tracking %+ Robotique et Vision (RV) %A Garrigues, Matthieu %A Manzanera, Antoine %< avec comité de lecture %B ICIAR %C Aveiro, Portugal %P 245 - 252 %8 2012 %D 2012 %R 10.1007/978-3-642-31295-3_29 %Z Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Conference papers %X This paper presents a new algorithm to track a high number of points in a video sequence in real-time. We propose a fast keypoint detector, used to create new particles, and an associated multiscale de-scriptor (feature) used to match the particles from one frame to the next. The tracking algorithm updates for each particle a series of appearance and kinematic states, that are temporally filtered. It is robust to hand held camera accelerations thanks to a coarse-to-fine dominant movement estimation. Each step is designed to reach the maximal level of data par-allelism, to target the most common parallel platforms. Using graphics processing unit, our current implementation handles 10 000 points per frame at 55 frames-per-second on 640 × 480 videos. %G English %2 https://inria.hal.science/hal-01118324/document %2 https://inria.hal.science/hal-01118324/file/parallel_tracking_iciar_submitted.pdf %L hal-01118324 %U https://inria.hal.science/hal-01118324 %~ ENSTA %~ ENSTA_U2IS